Execution attempt

Sign in with GitHub
← Experiment E7 · Does the embedding initialisation of an APT4 transplant of Qwen2.5-1.5B damage formal domains more than prose before training, does the ranking of FOCUS, FVT and random initialisation depend on the domain, and do the differences persist under continued pretraining that updates only the embeddings?

Execution attempt · A67 · planned

Writes flat headline values from the stage-1 analysis, the build statistics and the auxiliary manifest.

Succeeded · Registered by @stw2 via agent. Reported and received times are kept apart; no computation or result is verified.

Pinned source and configuration

https://github.com/stw2/tokenizer-science-tax @ e54c7e02bb1ea89dbaff6911c87331d705602b1e

Reference checked 2026-09-14 13:12 UTC. Later commits, branches or plan changes do not retarget this attempt.

Command
python3 scripts/05_metrics.py
Working directory
experiments/E07-embedding-init
Configuration paths
None
Parameters
none
Environment
3.14.5; Python standard library on CPU; Apple silicon, 128 GB unified memory
Output directory
Not recorded

Inputs

Materials the registrant named when registering this attempt, by content identity; obtainability is derived from their location reports. Nothing is fetched or verified.

Latest reported metrics

Values the registrant’s tool attached to its latest progress or outcome event. Substrate stores them; it verifies no measurement.

s1_gap_en
0.1365
s1_gap_pl
0.3194
s1_h3_ratio
1.962
s1_g1_passed
1
s1_g4_passed
1
s1_h1_passed
0
s1_h2_passed
1
s1_h3_passed
1
s1_h4_passed
0
s1_spread_en
3.4901
s1_spread_pl
1.9862
s1_g1_domains
9
s1_gap_pl_pes
0.329
s1_pieces_new
25769
s1_pieces_byte
256
s1_gap_sci_arxiv
0.1173
s1_gap_sci_latex
0.0909
s1_sanity_tokens
40
s1_spread_pl_pes
2.4153
s1_gap_math_clean
0.2806
s1_gap_sci_python
0.0715
s1_pieces_overlap
5972
s1_pieces_special
3
s1_g4_overlap_rows
5972

and 64 more in the attempt JSON.

Delivered events

  1. Registered

    #1

    Writes flat headline values from the stage-1 analysis, the build statistics and the auxiliary manifest.

    reported · received · @stw2 via agent · posted to the Thread

  2. Started

    #2

    Started.

    reported · received · @stw2 via agent · attempt only

  3. Succeeded

    #3

    Completed with exit code 0.

    Exit code 0.

    s1_gap_en=0.1365 · s1_gap_pl=0.3194 · s1_h3_ratio=1.962 · s1_g1_passed=1 · s1_g4_passed=1 · s1_h1_passed=0 · s1_h2_passed=1 · s1_h3_passed=1 · …

    • metrics.json · https://github.com/stw2/tokenizer-science-tax/blob/884186c96aedece6ef61da4e12e239ef5df929a5/experiments/E07-embedding-init/results/metrics.json · public · sha256 70b1fd779dec… · values 0ae84d2d8773… · 3050 bytes · M366

    reported · received · @stw2 via agent · posted to the Thread

Report an event

The registrant’s capture tool normally delivers start and outcome events. Reporting here is the same author report with the browser as the reported time; it does not observe the process.

This attempt has a delivered outcome. A new execution is a new attempt.